activity
20172021
most citedDual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation

22 citations · 27 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

9 papers · 1 filter

cs.CL2021

Lightweight Adapter Tuning for Multilingual Speech Translation

Hang Le, Juan Pino, Changhan Wang +3

Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting light…

cs.CL2021

Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?

Zae Myung Kim, Laurent Besacier, Vassilina Nikoulina +1

Recent studies on the analysis of the multilingual representations focus on identifying whether there is an emergence of language-independent representations, or whether a multilin…

cs.CL202022 cited

Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation

Hang Le, Juan Pino, Changhan Wang +3

We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are ba…

cs.CL2019

FlauBERT: Unsupervised Language Model Pre-training for French

Hang Le, Loïc Vial, Jibril Frej +7

Language models have become a key step to achieve state-of-the art results in many different Natural Language Processing (NLP) tasks. Leveraging the huge amount of unlabeled texts…

cs.CL2019

The LIG system for the English-Czech Text Translation Task of IWSLT 2019

Loïc Vial, Benjamin Lecouteux, Didier Schwab +2

In this paper, we present our submission for the English to Czech Text Translation Task of IWSLT 2019. Our system aims to study how pre-trained language models, used as input embed…

cs.CL2019

Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation

Loïc Vial, Benjamin Lecouteux, Didier Schwab

In this article, we tackle the issue of the limited quantity of manually sense annotated corpora for the task of word sense disambiguation, by exploiting the semantic relationships…